Samsung Collaborate With Japanese AI Startup for Producing AI Accelerator Chips

  • Collaboration with leading Japanese AI company will produce cutting-edge AI accelerator chips
  • Samsung Electronics To Provide Turnkey Semiconductor Solutions With 2nm GAA Process and 2.5D Package to Preferred Networks
Samsung Electronics is collaborating with Preferred Networks to offer turnkey semiconductor solutions. These solutions will feature a 2nm Gate-All-Around (GAA) process and a 2.5D packaging approach. The 2nm GAA process represents an advanced technology node, enabling smaller and more power-efficient chips.

By leveraging Samsung’s leading-edge foundry and advanced packaging products, Preferred Networks aims to develop powerful AI accelerators that meet the ever-growing demand for computing power driven by generative AI.

Since starting mass production of the industry’s first 3nm process node applying Gate-All-Around (GAA) transistor architecture, Samsung has strengthened its GAA technology leadership by successfully winning orders for the 2nm process with further upgrades in performance and power efficiency.

Meanwhile, the 2.5D packaging allows for stacking multiple dies, enhancing performance and miniaturization. This partnership aims to address the growing demand for high-performance chips in various applications, including artificial intelligence, data centers, and edge devices.

Preferred Networks (PFN) is a Japanese startup that focuses on the research and development of deep learning for IoT applications. The company was spun off from Preferred Infrastructure (PFI), which was founded by Toru Nishikawa, Daisuke Okanohara, and others in March, 2014. PFN aims to rapidly realize practical applications of cutting-edge technologies to solve real-world problems that are difficult to address with existing solutions.

Based on this collaboration, Samsung and Preferred Networks plan to showcase groundbreaking AI chiplet solutions for the next-generation data center and generative AI computing market in the future.

Post a Comment

Previous Post Next Post